HIDDEN MINIMA IN TWO-LAYER RELU NETWORKS

被引：0
|
作者：
Arjevani, Yossi [1 ]
机构：
[1] The Hebrew University, Jerusalem, Israel
来源：
arXiv | 2023年
关键词：
Compilation and indexing terms; Copyright 2024 Elsevier Inc;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Eigenvalues and eigenfunctions - Group theory
引用
收藏
相关论文
共 50 条
  • [1] Annihilation of Spurious Minima in Two-Layer ReLU Networks
    Arjevani, Yossi
    Field, Michael
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [2] Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
    Safran, Itay
    Shamir, Ohad
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [3] Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II
    Arjevani, Yossi
    Field, Michael
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [4] Convergence Analysis of Two-layer Neural Networks with ReLU Activation
    Li, Yuanzhi
    Yuan, Yang
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [5] A Global Universality of Two-Layer Neural Networks with ReLU Activations
    Hatano, Naoya
    Ikeda, Masahiro
    Ishikawa, Isao
    Sawano, Yoshihiro
    [J]. JOURNAL OF FUNCTION SPACES, 2021, 2021
  • [6] Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent
    Holzmueller, David
    Steinwart, Ingo
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23
  • [7] Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent
    Holzmüller, David
    Steinwart, Ingo
    [J]. Journal of Machine Learning Research, 2022, 23
  • [8] Expressive Numbers of Two or More Hidden Layer ReLU Neural Networks
    Inoue, Kenta
    [J]. 2019 SEVENTH INTERNATIONAL SYMPOSIUM ON COMPUTING AND NETWORKING WORKSHOPS (CANDARW 2019), 2019, : 129 - 135
  • [9] Learning behavior and temporary minima of two-layer neural networks
    Annema, Anne-Johan
    Hoen, Klaas
    Wallinga, Hans
    [J]. Neural Networks, 1994, 7 (09): : 1387 - 1404
  • [10] Training a Two-Layer ReLU Network Analytically
    Barbu, Adrian
    [J]. SENSORS, 2023, 23 (08)
12345